Hani Goodarzi
@genophoria
Core Investigator @arcinstitute | Associate Professor @Ucsf_Biochem @UCSFurology @UCSFCancer | {Computational, Cancer, RNA} biologist
@iamjohnnyyu, @nalidoust, and I are excited to tell you about Tahoe-100M! The largest publicly available single-cell dataset that measures the effect of 1200 genes on 50 cell line models. The @vevo_ai team has outdone itself. #tahoe100M #Tahoe100M biorxiv.org/content/10.110…
Also, be sure to check out Alex’s work on AI-enabled neuroanatomy this Saturday at ICML's Foundation Models for Life Sciences Workshop!
Heading to Vancouver tomorrow for ICML and a visit to UBC! Ping me if you’re in town and want to catch up over tea/coffee!
Our 2nd Annual Investigator Retreat wrapped up with talks covering immunology and technology development from Core Investigators @ChristophThaiss and @FelixHorns, our incoming Science Fellow @maya_arce_, and our Innovation Investigators and Ignite Awardees @icclarker, Calvin Kuo,…
Our work on "Evaluating the representational power of pre-trained DNA language models for regulatory genomics" led by @AmberZqt with help from @NiraliSomia & @stevenyuyy is finally published in Genome Biology! Check it out! genomebiology.biomedcentral.com/articles/10.11…
Do current genomic language models (pre-trained on whole genomes) learn a foundational understanding of biology in the non-coding region of human genomes? A new evaluation led by @AmberZqt suggests not yet! 1/N paper: biorxiv.org/content/10.110…
It’s incredible that this IMO gold medal–level model isn’t using any specialized mathematical proof tools like Lean, but instead relies entirely on pure textual reasoning. This strongly reinforces the foundation of our BioReason model (arxiv.org/abs/2505.23579 ), which applies…
1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).
We love it when others build dev tools for building on Tahoe-100M. Today, we highlight scDataset in our @tahoe_ai blog. Developed by @davide_dascenzo & @sebacultrera, it makes it easier to train DL models on datasets with the daunting scale of Tahoe-100M (see poster in ICML '25)
Very excited to share our new work on gastruloids by the incredible @ugcgccacc! We mapped gene expression across 26 individual gastruloids at single-cell resolution and discovered some pretty amazing patterns about how these "mini-embryos" organize themselves.
Inspired by tools like ChatGPT, @UHN researchers are creating powerful AI models that can read and understand DNA, RNA and proteins — all at the same time — to better predict how cells behave and how diseases develop ➜ bit.ly/44uZIZB @UHN_Research @BoWang87
Today we at @WCMEnglanderIPM submitted our response to the NIH's call for a national AI strategy, titled "Leading the Transformation: A National Artificial Intelligence Strategy for the NIH" @FaltasLab @cnsternberg @JanKrumsiek @hajirasouliha 1/6
While I’m a big fan of new technologies that help us study human biology…there’s still no replacement for animal research! I wrote an article outlining this in @GENbio genengnews.com/topics/transla…
New notebook for training Arc's State model for the Virtual Cell Challenge. While not exactly what State was designed for, hopefully a helpful resource for getting started. Look forward to seeing some, um State-ful models on the leaderboard ;). colab.research.google.com/drive/1QKOtYP7…
Proud to share a big step toward building systems that help us simulate and predict the behavior of cells! GREmLN is a graph-based transformer model, designed to reason across biological data by embedding gene regulatory network architecture directly into its attention…
🚨 Just dropped! GREmLN is a graph-based transformer model that uses the molecular logic of cells to enable insights into disease states. This nimble model accounts for causality + locality using gene regulatory networks📄 Read the preprint: bit.ly/44lLF8x
Just had the pleasure of being interviewed by @Nature on the rise of AI in digital pathology. With growing workloads and global shortages of pathologists, the field is turning to AI not as a luxury—but as a necessity. Full article: nature.com/articles/d4158… In the article, I…
Come join the bridge editing team @arcinstitute and build the future of genome design!
Happy to share that I'm continuing my research on bridge recombinases as a scientist in @pdhsu lab at the @arcinstitute! I am looking for a motivated post-grad to work with me as a research associate. If you are interested or know of someone, please use the link below:
Excellent piece explaining year 1 of our Virtual Cell Challenge!
Last week @arcinstitute released the Virtual Cell Challenge 🧬 The goal is to train a model capable of simulating a cell. I wrote a primer for engineers without a biology background.
Core Investigator @li_lingyin's new paper in @NatChemBio investigates why human STING inhibitors have shown limited efficacy, despite strong activity in mouse models. The study, led by @xujun_cao and @rjchan426, finds that the commonly targeted site on STING is not required for…
Very happy to share Minh Nguyen's paper with @WilliamCChen1 from @LabRaleigh reporting optimized CNA size thresholds and co-occurence patterns for individualized risk-stratifictation. @NeurosurgUCSF @UCSFRadOnc @UCSFCancer @UCSF @akashjp330 . nature.com/articles/s4146…
In this Q&A with @NikoMcCarty, Jain discusses her group's latest discoveries, the revival of mechanistic research into vitamins, and how Arc enables her metabolite-centric approach: arcinstitute.org/news/meet-isha…
Hello RNA World! Ever wonder what's "talking to" your favorite transcript, but were too scared to ask? In our review in @CellReports, @FKHM and I highlight new RNA-focused tools for discovering RNA interactions across organizational scales. Checkit! tinyurl.com/ydn6e3ac
Welcome @ishahjain, Arc's eighth Core Investigator! Jain has spent more than a decade studying how the human body senses, and responds to, external molecules—especially oxygen and vitamins.